Roar AI
DiscordGet started
OpenAI

OpenAI API in Sri Lanka

Use OpenAI models through one API, with pricing in Sri Lankan rupees and usage on one monthly invoice. No separate OpenAI account or foreign card needed.

OpenAI models and prices in rupees

ModelInput / 1MOutput / 1MContextBest forProcessed in
LKR 3,330LKR 16,6501.05MHard maths, science and agent tasksGlobal
Cached inputLKR 333LKR 4,163 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 1,665LKR 8,325Results within 24 hours, for work nobody is waiting on.
Long requestsLKR 6,660LKR 24,975Above 272,000 input tokens, the whole request is billed at these rates.
Everything about GPT-6 Astra
LKR 2,664LKR 13,3201.05MHard science and mathsGlobal
Cached inputLKR 133LKR 3,330 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 1,332LKR 6,660Results within 24 hours, for work nobody is waiting on.
Long requestsLKR 5,328LKR 19,980Above 272,000 input tokens, the whole request is billed at these rates.
Everything about GPT-6.2 Astra
LKR 1,332LKR 6,6601.05MLong coding tasksGlobal
Cached inputLKR 133LKR 1,665 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 666LKR 3,330Results within 24 hours, for work nobody is waiting on.
Long requestsLKR 2,664LKR 9,990Above 272,000 input tokens, the whole request is billed at these rates.
Everything about GPT-5.6 Sol
LKR 666LKR 3,3301.05MEveryday work and agentsGlobal
Cached inputLKR 33.30LKR 833 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 333LKR 1,665Results within 24 hours, for work nobody is waiting on.
Long requestsLKR 1,332LKR 4,995Above 272,000 input tokens, the whole request is billed at these rates.
Everything about GPT-6.2 Sol
LKR 666LKR 3,3301.05MProduction coding agentsGlobal
Cached inputLKR 33.30LKR 833 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 333LKR 1,665Results within 24 hours, for work nobody is waiting on.
Long requestsLKR 1,332LKR 4,995Above 272,000 input tokens, the whole request is billed at these rates.
Everything about GPT-6.1 Sol
LKR 666LKR 3,3301.05MProducts already built on GPT-6 SolGlobal
Cached inputLKR 66.60LKR 833 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 333LKR 1,665Results within 24 hours, for work nobody is waiting on.
Long requestsLKR 1,332LKR 4,995Above 272,000 input tokens, the whole request is billed at these rates.
Everything about GPT-6 Sol
LKR 583LKR 4,662400KTerminal coding agentsGlobal
Cached inputLKR 58.28—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
Everything about GPT-5.3-Codex
LKR 66.60LKR 4001.05MHigh-volume extractionGlobal
Cached inputLKR 6.66LKR 83.25 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 33.30LKR 200Results within 24 hours, for work nobody is waiting on.
Long requestsLKR 133LKR 599Above 272,000 input tokens, the whole request is billed at these rates.
Everything about GPT-5.6 Luna
LKR 66.60LKR 416400KClassification and tagging at scaleGlobal
Cached inputLKR 6.66—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 33.30LKR 208Results within 24 hours, for work nobody is waiting on.
Everything about GPT-5.4 nano
LKR 64.94LKR 260131KMaths, science and logicGlobal
Cached inputLKR 32.47—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
Everything about gpt-oss-120b
LKR 33.30LKR 1671.05MHigh-volume extraction and routingGlobal
Cached inputLKR 3.33LKR 41.63 to write—Repeat a long prompt prefix and those tokens bill at this rate. Automatic.
BatchLKR 16.65LKR 83.25Results within 24 hours, for work nobody is waiting on.
Long requestsLKR 66.60LKR 250Above 272,000 input tokens, the whole request is billed at these rates.
Everything about GPT-6 Luna
LKR 30.30LKR 108131KQuick reasoning stepsGlobal
Standard rates only. Everything about gpt-oss-20b
LKR 4,995
characters
——Real-time voice repliesGlobal
Standard rates only. Everything about TTS-1
LKR 4,810
audio seconds
——Transcripts and captionsGlobal
Standard rates only. Everything about Whisper large-v3-turbo
LKR 43.29—8KMultilingual search and retrievalGlobal
BatchLKR 21.65FreeResults within 24 hours, for work nobody is waiting on.
Everything about text-embedding-3-large
LKR 6.66—8KLow-cost search and retrievalGlobal
BatchLKR 3.33FreeResults within 24 hours, for work nobody is waiting on.
Everything about text-embedding-3-small

Rupee prices are our published US dollar rates converted at LKR 333 to the dollar, our rate for November 2026 — the same rate your invoice uses.

Which OpenAI model to use

The newest everyday model, for writing, analysis and agents at volume.

The flagship, for advanced science and maths, where the answer can wait.

Production coding agents, professional documents and spreadsheet work.

The cheapest GPT-6, for sorting, extracting and routing at volume with a million-token context.

Classifying, tagging and ranking large volumes of text.

Search and retrieval over your own documents, including languages other than English.

Transcripts and captions in 99 languages, Sinhala and Tamil among them.

Calling the OpenAI API from Sri Lanka

The Roar AI gateway speaks the OpenAI API format. Point the OpenAI SDK at Roar AI and name a OpenAI model; moving to another provider’s model later is a change to the model name.

from openai import OpenAI

client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")

reply = client.chat.completions.create(
    model="gpt-6.2-sol",
    messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)

Read the API docs.

Where OpenAI requests are processed

OpenAI models are processed on international infrastructure, outside Sri Lanka. None of them is hosted locally.

If a workload’s data has to stay in the country, Qwen 3.8 27B LK runs on our own server in Colombo.

Questions

Can I use the OpenAI API from Sri Lanka?

Yes. Every OpenAI model listed on this page is available from Sri Lanka through Roar AI’s API, on the same key as every other model on the platform.

Can I pay for the OpenAI API in Sri Lankan rupees?

Yes. OpenAI usage is billed to one monthly invoice in LKR, together with any other models your team uses.

Do I need a separate account with OpenAI?

No. One Roar AI key reaches every OpenAI model listed here, so there is no separate OpenAI account or foreign card to set up.

Is the OpenAI API hosted in Sri Lanka?

No. OpenAI models are processed outside Sri Lanka. Roar AI’s locally hosted model, Qwen 3.8 27B LK, is a separate model and is labelled as such.

OpenAI from Sri Lanka,
billed in rupees

One key for every OpenAI model and every other model, on one monthly invoice in LKR.